Global S&T Development Trend Analysis Platform of Resources and Environment
DOI | 10.1038/s41467-017-00564-x |
Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline | |
Tang, Ziqi1,2,3; Chuang, Kangway, V1,2; DeCarli, Charles4; Jin, Lee-Way5; Beckett, Laurel6; Keiser, Michael J.1,2; Dugger, Brittany N.7 | |
2019-05-15 | |
发表期刊 | NATURE COMMUNICATIONS |
ISSN | 2041-1723 |
出版年 | 2019 |
卷号 | 10 |
文章类型 | Article |
语种 | 英语 |
国家 | USA; Peoples R China |
英文摘要 | Neuropathologists assess vast brain areas to identify diverse and subtly-differentiated morphologies. Standard semi-quantitative scoring approaches, however, are coarse-grained and lack precise neuroanatomic localization. We report a proof-of-concept deep learning pipeline that identifies specific neuropathologies-amyloid plaques and cerebral amyloid angiopathy-in immunohistochemically-stained archival slides. Using automated segmentation of stained objects and a cloud-based interface, we annotate >70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieve strong plaque classification on a 10-WSI hold-out set (0.993 and 0.743 areas under the receiver operating characteristic and precision recall curve, respectively). Prediction confidence maps visualize morphology distributions at high resolution. Resulting network-derived amyloid beta (A beta)-burden scores correlate well with established semiquantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrates that networks learn patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist's ability suggests a route to neuropathologic deep phenotyping. |
领域 | 资源环境 |
收录类别 | SCI-E |
WOS记录号 | WOS:000468023200011 |
WOS关键词 | CEREBRAL AMYLOID ANGIOPATHY ; NEUROPATHOLOGIC ASSESSMENT ; ASSOCIATION GUIDELINES ; NATIONAL INSTITUTE ; DIGITAL PATHOLOGY ; NEURITIC PLAQUES ; SENILE PLAQUES ; HUMAN BRAIN ; CONSORTIUM ; ESTABLISH |
WOS类目 | Multidisciplinary Sciences |
WOS研究方向 | Science & Technology - Other Topics |
URL | 查看原文 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://119.78.100.173/C666/handle/2XK7JSWQ/203438 |
专题 | 资源环境科学 |
作者单位 | 1.Univ Calif San Francisco, Dept Pharmaceut Chem, Dept Bioengn & Therapeut Sci, Inst Neurodegenerat Dis, 675 Nelson Rising Ln Box 0518, San Francisco, CA 94143 USA; 2.Univ Calif San Francisco, Bakar Computat Hlth Sci Inst, 675 Nelson Rising Ln Box 0518, San Francisco, CA 94143 USA; 3.Tsinghua Univ, Sch Pharmaceut Sci, Beijing 100084, Peoples R China; 4.Univ Calif Davis, Sch Med, Dept Neurol, 4860 Y St Suite 3700, Sacramento, CA 95817 USA; 5.Univ Calif Davis, Sch Med, Dept Pathol & Lab Med, 2805 50th St, Sacramento, CA 95817 USA; 6.Univ Calif Davis, Dept Publ Hlth Sci, Med Sci, 1C One Shields Ave, Davis, CA 95616 USA; 7.Univ Calif Davis, Sch Med, Dept Pathol & Lab Med, 3400A Res Bldg 3, Davis, CA 95817 USA |
推荐引用方式 GB/T 7714 | Tang, Ziqi,Chuang, Kangway, V,DeCarli, Charles,et al. Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline[J]. NATURE COMMUNICATIONS,2019,10. |
APA | Tang, Ziqi.,Chuang, Kangway, V.,DeCarli, Charles.,Jin, Lee-Way.,Beckett, Laurel.,...&Dugger, Brittany N..(2019).Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline.NATURE COMMUNICATIONS,10. |
MLA | Tang, Ziqi,et al."Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline".NATURE COMMUNICATIONS 10(2019). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论